VARGPT-v1.1: Improve Visual Autoregressive Large Unified Model via Iterative Instruction Tuning and Reinforcement Learning.

PiCo: Jailbreaking Multimodal Large Language Models via <i>Pi</i>ctorial <i>Co</i>de Contextualization.

ATRI: Mitigating Multilingual Audio Text Retrieval Inconsistencies by Reducing Data Distribution Errors.

Do we really have to filter out random noise in pre-training data for language models?

VARGPT: Unified Understanding and Generation in a Visual Autoregressive Multimodal Large Language Model.

Human Motion Capture and Recognition Based on Sparse Inertial Sensor.

Label Design and Extraction in High-Temperature Logistics Based on Concave Coding and MLFFA-DeepLabV3+ Network.

Real-Time Wheat Unsound Kernel Classification Detection Based on Improved YOLOv5.

FedSOV: Federated Model Secure Ownership Verification with Unforgeable Signature.

FedZKP: Federated Model Ownership Verification with Zero-knowledge Proof.